Integral Fast Fourier Color Constancy

TL;DR

The paper introduces IFFCC, a fast and accurate multi-illuminant color constancy algorithm that outperforms neural networks in speed and parameter efficiency, enabling real-time auto white balance in complex scenes.

Contribution

It extends the FFCC algorithm to multi-illuminant scenes using integral UV histograms and parallel Fourier convolutions for high-speed, high-accuracy auto white balance.

Findings

Achieves comparable or better accuracy than neural networks.

Reduces parameter count by over 400 times.

Processes 20 to 100 times faster than neural network methods.

Abstract

Traditional auto white balance (AWB) algorithms typically assume a single global illuminant source, which leads to color distortions in multi-illuminant scenes. While recent neural network-based methods have shown excellent accuracy in such scenarios, their high parameter count and computational demands limit their practicality for real-time video applications. The Fast Fourier Color Constancy (FFCC) algorithm was proposed for single-illuminant-source scenes, predicting a global illuminant source with high efficiency. However, it cannot be directly applied to multi-illuminant scenarios unless specifically modified. To address this, we propose Integral Fast Fourier Color Constancy (IFFCC), an extension of FFCC tailored for multi-illuminant scenes. IFFCC leverages the proposed integral UV histogram to accelerate histogram computations across all possible regions in Cartesian space and parallelizes Fourier-based convolution operations, resulting in a spatially-smooth illumination map. This approach enables high-accuracy, real-time AWB in multi-illuminant scenes. Extensive experiments show that IFFCC achieves accuracy that is on par with or surpasses that of pixel-level neural networks, while reducing the parameter count by over $400\times$ and processing speed by 20 - $100\times$ faster than network-based approaches.